Per-request emotion steering for vLLM, with batching preserved
Per-request emotion steering that preserves vLLM continuous batching for Qwen3.
Emotional probes for Gemma 4 E4B
Anthropic's emotion research replicated open-source with a Flask visualizer for Gemma 4.
ML researchers and mechanistic interpretability engineers
TransformerLens · Neuronpedia
Per-request emotion steering that preserves vLLM continuous batching for Qwen3.
High-throughput vLLM API for per-request emotion steering beats prompt-only methods.
Pure math kernel produced emergent behavior — one instance started dreaming unprompted.
Sub-cent CPU-only voice agent with vision-keyed proactivity beats cloud APIs on cost.
Emotion clouds and AI coaching, but Moodpath and Woebot already solve this better.
Three.js goo blob emotionally maps to Claude via MCP—playful but niche desktop-only novelty.