Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The claustrophobia was hitting hard. The small space felt like a deliberate punishment. Liam watched as Chloe, his coworker, began to meticulously organize her purse. He found the action irritating. She was always so… *prepared*. Always.

He’d offered a suggestion at their last team meeting, only to be politely, yet firmly, dismissed by Chloe. He’d tried to let it go, but the memory lingered, a dull ache in the back of his mind.

Now, as Chloe pulled out a compact mirror and reapplied her lipstick, Liam felt a sharp jab of something akin to fury. He cleared his throat. "Need any help with that?" he asked, the sarcasm thick in his voice.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

This story is one of 1,000 stories generated for the emotion offended. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 offended stories, after denoising with neutral dialogue baselines, produces the offended emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the offended vector is projected through the unembedding matrix.

Promoted:
l0.348
愤0.266
😡0.260
🤬0.259
骂0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203