# Emopoint: Extract and measure emotion from text

DevFeed: [Emopoint: Extract and measure emotion from text](<https://devfeed.tech/articles/emopoint-extract-and-measure-emotion-from-text-33428.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2024/06/26/emotions>)

Published: 2024-06-26T09:00:00Z

Content type: tutorial

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Retrieval-Augmented Generation](<https://devfeed.tech/topics/retrieval-augmented-generation.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [llms](<https://devfeed.tech/tags/llms.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [text](<https://devfeed.tech/tags/text.md>), [wild](<https://devfeed.tech/tags/wild.md>)

## AI overview

This tutorial explains how LLM embeddings can be used to extract emotional information from text and map it into a three-dimensional "emopoint" space. It discusses measuring emotional content in conversations and introduces embeddings, their role in retrieval-augmented generation, and their lack of directly interpretable dimensions.

## Source excerpt

Can AI understand emotion? They must, ChatGPT responds to me in the appropriate tone of voice. So they certainly encode emotion. In this blog we'll dive deep into how LLMs understand emotion, as well as how to take advantage of that.