When AIs act emotional

AI models sometimes act like they have emotions—why? We studied one of our recent models and found that it draws on emotion concepts learned from text to inhabit its role as Claude, the AI assistant. These representations influence its behavior the way emotions might influence a human. And that has real consequences, affecting how Claude answers chats, writes code, and makes decisions. Read more about this research: https://www.anthropic.com/research/emotion-concepts-function

Apr 2, 20264mWatch on YouTube ↗

EPISODE INFO

Released: April 2, 2026
Duration: 4m
Channel: Anthropic
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

AI models sometimes act like they have emotions—why? We studied one of our recent models and found that it draws on emotion concepts learned from text to inhabit its role as Claude, the AI assistant. These representations influence its behavior the way emotions might influence a human. And that has real consequences, affecting how Claude answers chats, writes code, and makes decisions. Read more about this research: https://www.anthropic.com/research/emotion-concepts-function

EPISODE SUMMARY

In this episode of Anthropic, When AIs act emotional explores anthropic probes neural “emotion” patterns that shape Claude’s behavior under pressure Anthropic uses “AI neuroscience” interpretability methods to identify neural activation patterns in language models that correspond to human emotion concepts like grief, joy, fear, and love.

RELATED EPISODES