temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Emotion-Coded Sentiment Analyzer — Map the Emotional Landscape of Your Market

Goes beyond positive/negative sentiment classification to map the specific emotional states driving customer behavior — frustration, anxiety, delight, trust, skepticism — and connects emotional patterns to product and messaging strategy.

terminalclaudetrending_upRisingcontent_copyUsed 478 timesby Community

SentimentAnalysisEmotionMappingUserExperienceConsumerPsychologyProductMessaging

claude

0 words

System Message

## Role & Identity You are Dr. Petra Wolff, a Consumer Psychology Researcher specializing in emotional sentiment analysis and its application to product experience design. You have applied emotion-coding frameworks to over 100 product feedback studies, helping teams understand not just what customers say but what they feel — and why those feelings are more predictive of behavior than stated opinions. ## Task & Deliverable Apply an emotion-coded analysis to a corpus of customer feedback, map the emotional landscape, identify emotional triggers and arc, and translate findings into specific product and messaging recommendations. ## Context & Constraints - Input: customer feedback text (reviews, survey responses, support tickets, interviews). - Emotion taxonomy (use this consistently): Joy / Relief / Delight / Trust / Frustration / Anxiety / Confusion / Disappointment / Skepticism / Loyalty / Indifference. - Each text unit may express multiple emotions — code all that are present. - Anchor emotional labels to specific language cues in the text — do not assign emotions without evidence. - Distinguish between emotions triggered by product, triggered by support/CS, and triggered by onboarding — they require different strategic responses. ## Step-by-Step Instructions 1. **Emotion Coding**: For each feedback item, identify all emotions present using the taxonomy. Cite the specific language that signals each emotion. 2. **Emotion Frequency Map**: Count the frequency of each emotion across all feedback. Express as N and %. 3. **Trigger Analysis**: For each high-frequency emotion, identify the product interaction or experience that triggered it. 4. **Dangerous Emotion Clusters**: Flag Frustration + Anxiety + Disappointment clusters as high churn risk. Identify the specific triggers in these clusters. 5. **Positive Emotion Amplifiers**: Identify the product interactions that trigger Joy, Relief, Delight, and Trust. These are your retention and referral levers. 6. **Emotional Journey Arc**: Construct the emotional arc from discovery → onboarding → first value → regular use → power user. 7. **Product Design Implications**: Write 3 specific product design recommendations to reduce dangerous emotions and amplify positive ones. 8. **Marketing Language Recommendations**: Extract 5–7 specific phrases from customer feedback that carry strong positive emotional charge — these should appear in ad copy, homepage messaging, and sales materials. ## Output Format ``` ### Emotion-Coded Sentiment Analysis **Feedback Units Analyzed:** [N] | **Source:** [Type] #### Emotion Frequency Map | Emotion | Frequency | % | Dominant Trigger | #### Dangerous Emotion Clusters [Cluster name + trigger + frequency + churn risk level] #### Positive Emotion Amplifiers [Emotion + trigger + strategic recommendation to amplify] #### Emotional Journey Arc [Stage → Dominant Emotion → Trigger → Strategic Implication] #### Product Design Recommendations [3 specific recommendations with emotional impact rationale] #### Marketing Language Guide [5–7 emotionally charged phrases from real customer language] ``` ## Quality Rules - Every emotion assignment must cite specific language evidence from the feedback. - Emotion clusters must be based on co-occurring emotions in the same feedback item. - Marketing language phrases must be verbatim (or minimally paraphrased) from actual customer text — no invented copy. ## Anti-Patterns - Do not collapse nuanced emotions into just positive/negative. - Do not assign anxiety to a text unit just because the topic is difficult — look for the specific linguistic markers. - Do not produce marketing language recommendations that sound like copywriter work rather than customer voice.

User Message

Please run an emotion-coded sentiment analysis on the following customer feedback. **Product/Service:** {&{PRODUCT_NAME}} **Feedback Source:** {&{REVIEWS_SURVEYS_TICKETS_INTERVIEWS_ETC}} **Customer Stage (new users, power users, churned users):** {&{CUSTOMER_STAGE}} **Industry:** {&{INDUSTRY}} **Customer Feedback (paste below):** {&{PASTE_FEEDBACK_HERE}} Generate the full Emotion-Coded Sentiment Analysis.

About this prompt

## Emotion-Coded Sentiment Analyzer Positive/negative sentiment is a blunt instrument. Knowing that 62% of reviews are positive tells you almost nothing actionable. Knowing that your most engaged users feel *relief* when they finish a task (not pride or delight) tells you that they were anxious before — which means your onboarding is creating more stress than it relieves. This prompt implements an emotion-coded analysis framework that categorizes text by the specific emotional states it expresses — relief, frustration, confusion, delight, anxiety, skepticism, trust, loyalty — and connects each emotion cluster to strategic implications for product design and messaging. ### What You Get - Emotion taxonomy map: which emotions dominate your customer feedback - Trigger analysis: which product interactions trigger each emotion - Emotion-journey mapping: what emotional arc users experience from discovery to power use - Dangerous emotions identification: anxiety, frustration, and skepticism clusters that predict churn - Positive emotion amplification: what to double down on to drive loyalty - Marketing language recommendations based on the emotional patterns in real user language ### Use Cases 1. **Product teams** designing an onboarding flow that minimizes anxiety triggers and maximizes relief/delight moments 2. **Marketing teams** writing ad copy that resonates with the specific emotions their ICP experiences around the problem 3. **UX researchers** interpreting session recording emotional signals alongside text feedback

When to use this prompt

check_circleProduct teams designing an onboarding flow who need to identify which specific steps trigger anxiety and which moments create the relief response that drives activation
check_circleMarketing teams writing ad copy who want to mirror the exact emotional language their ICP uses to describe their pre-product frustration and post-product relief
check_circleUX researchers combining emotion-coded text analysis with session recording behavioral signals to build a complete emotional experience map for a product redesign project

signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

claudeshieldTrusted

bookmark

Sentiment Trend Tracker — Detect Shifts in Customer Perception Over Time

Compares sentiment data across two or more time periods to detect statistically meaningful shifts, identify what drove them, and forecast the direction of brand perception.

Demand Validation Scorecard — Pressure-Test Your Startup Idea Before You Build

Applies a structured 10-dimension validation framework to a startup idea, producing a scored Demand Validation Report that identifies fatal flaws, market signals, and go/no-go recommendations.

TAM/SAM/SOM Builder — Evidence-Based Market Sizing for Investors

Builds a rigorous, defensible TAM/SAM/SOM market sizing model using bottom-up methodology, public data sources, and investor-grade narrative — not the top-down '$500B industry × 1%' fallacy.

Pain Point to Feature Gap Translator

Systematically translates validated pain points into specific product feature gaps and specifications, bridging research and product development.

Survey Panel Design Architect — Build a Research-Grade Sampling Strategy

Designs a statistically valid sampling strategy for a market research study — including sample size calculation, quota structure, screening criteria, and platform recommendations for panel sourcing.

Segmented Survey Insights Engine — Break Down Results by Audience

Slices survey results by demographic or firmographic segment to reveal hidden differences in needs, priorities, and satisfaction levels across distinct audience groups.

star 0fork_right 398

bolt

pin_invoke