# LLMs Have Emotions: Claude's Internals Reveal Steerable Emotion Vectors

> Anthropic's new research gives us the first direct look at causally steerable emotion vectors inside a large language model. That should change how we think about AI.

---

LLMS index: [llms.txt](/llms.txt)

---

[![featured](/img/hero/ai/ai-emotion.webp)](https://vonng.com/en/ai/ai-emotion/)

Anthropic's new research gives us the first direct look at causally steerable emotion vectors inside a large language model. That should change how we think about AI. [**Read more**](https://vonng.com/en/ai/ai-emotion/)