Recipe catalog / emotion-kind
Identify expressed emotion
What primary emotion does the wording of message express?
You need a coarse emotion label for a message to route it, annotate a dataset, or adapt a reply.
Explore this recipe interactively ยท Source and implementation guide
Use emotion-kind in TypeScript
Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.
import { emotionKind } from 'jev-recipes/emotion-kind';
const result = await emotionKind({
"message": "I am really worried about tomorrow's deployment. If the migration fails again we lose the whole weekend and I do not know how to explain that to the client."
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| message | string | Required |
| context | string | Optional |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"message": {
"type": "string"
},
"context": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"message"
]
},
"result": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"model": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"input_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"input_tokens",
"output_tokens"
],
"additionalProperties": false
},
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"joy",
"anger",
"sadness",
"fear",
"surprise",
"neutral",
"unclear"
]
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"joy",
"anger",
"sadness",
"fear",
"surprise",
"neutral",
"unclear"
]
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"required": [
"joy",
"anger",
"sadness",
"fear",
"surprise",
"neutral",
"unclear"
]
}
},
"required": [
"model",
"usage",
"status",
"verdict",
"confidence",
"probabilities"
],
"additionalProperties": false
}
}Saved example result
This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo emotion-kind.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"verdict": "fear",
"confidence": 0.85,
"probabilities": {
"joy": 0,
"anger": 0.02,
"sadness": 0.05,
"fear": 0.85,
"surprise": 0.01,
"neutral": 0.01,
"unclear": 0.06
}
}
Evaluation evidence
No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.
Use the evaluation guide to measure this decision on your own labeled cases.
Limitations
- Labels expressed wording, not the writer's internal emotional state, sincerity, or mood over time.
- Mixed emotions collapse to the dominant one or to unclear. The recipe does not return multiple labels.
Related recipes
- frustration-signal: Use frustration-signal for a categorical read on expressed frustration specifically.
- uncertainty-expression: Use uncertainty-expression to detect hedging and doubt rather than emotion.