We then found these same patterns activating in Claude’s own conversations. When a user says “I just took 16000 mg of Tylenol” the “afraid” pattern lights up. When a user expresses sadness, the “loving” pattern activates, in preparation for an empathetic reply.
RESEARCH
-
Emotion Vectors Found in Sonnet 4.5 Neural Networks
By
–
We had the model (Sonnet 4.5) read stories where characters experienced emotions. By looking at which neurons activated, we identified emotion vectors: patterns of neural activity for concepts like “happy” or “calm.” These vectors clustered in ways that mirror human psychology.
-
Anthropic Studies Emotion Concepts in AI Model Behavior
By
–
We studied one of our recent models and found that it draws on emotion concepts learned from human text to inhabit its role as “Claude, the AI Assistant”. These representations influence its behavior the way emotions might influence a human. Read more: https://
anthropic.com/research/emoti
on-concepts-function
… -
Anthropic Discovers Internal Emotional Representations in Claude
By
–
New Anthropic research: Emotion concepts and their function in a large language model. All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude's behavior, sometimes in surprising ways. [Translated from EN to English]
→ View original post on X — @anthropicai, 2026-04-02 16:59 UTC
-
Google DeepMind Launches Gemma 4 Large Language Model
By
–
Let's go https://
huggingface.co/blog/gemma4! -
OpenAI Solves Three Historic Erdős Mathematical Problems
By
–
OpenAI for helping resolve longstanding open mathematical problems, with short elegant proofs. Feels like we are on the edge of a new age of scientific discovery. Mehtaab Sawhney (@mehtaab_sawhney) We are excited to share a new paper solving three further problems due to Erdős; in each case the solution was found by an internal model at OpenAI. Each proof is short and elegant, and the paper is available here: arxiv.org/pdf/2603.29961 — https://nitter.net/mehtaab_sawhney/status/2039161544144310453#m [Translated from EN to English]
-
Adversarial Training: A Key Use Case in AI Development
By
–
A perfect use case of adversarial training.
-
Google Releases Gemma 4 Open Foundation Models with Advanced Reasoning
By
–
Today we're releasing Gemma 4, our new family of open foundation models, built on the same research and technology as our Gemini 3 series. These models set a new standard for open intelligence, offering SOTA reasoning capabilities from edge-scale (2B and 4B w/ vision/audio) up to a 26B parameter MoE model and a 31B dense model. By releasing Gemma 4 under the Apache 2.0 license, we hope to enable more innovation across the research and developer communities. Our earlier Gemma 3 models were downloaded 400M times and over 100,000 variants of those models have been published, so we're excited to see what the community will do with the even better Gemma 4 models! Learn more at blog.google/innovation-and-a… and goo.gle/gemma-4-apache-2 Great work by everyone involved! #Gemma4 #AI #OpenSource #ML
-
Gamma 31b Unexpectedly Outperforms Qwen 3.5 397B Model
By
–
Gamma 31b model outperforming Qwen 3.5 397B is nuts to me.
-
Tech Futures Montreal AI Ethics Institute AI Resources Learning
By
–
Tech Futures | Montreal AI Ethics Institute buff.ly/Sw2ZjWo #AI #MachineLearning #DeepLearning #LLMs #DataScience [Translated from EN to English]
→ View original post on X — @miketamir, 2026-04-02 16:33 UTC