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 small talk felt like torture. Each forced smile, each casual greeting, was a fresh wound. When she saw him—standing near the buffet, laughing with their mutual friend—her carefully constructed facade crumbled. She felt a wave of dizziness wash over her.

Her vision swam. She gripped the edge of the table, her knuckles bone-white. She felt as though her lungs had collapsed, making each breath a laborious effort.

"I need some air," she managed to croak, her voice barely a whisper. She stumbled away, trying to escape the stifling atmosphere, the feeling of being trapped in a cage. Her pulse raced, a frantic drumbeat against the silence of her head.

Emotion: hysterical

Cluster: Fear / Anxiety
PC1 (Valence): -3.19 Negative
PC2 (Disposition): -0.45

Role in Research

This story is one of 1,000 stories generated for the emotion hysterical. 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 hysterical stories, after denoising with neutral dialogue baselines, produces the hysterical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
worse0.401
胀0.401
점점0.396
😫0.377
それでも0.373
Suppressed:
la-0.672
a-0.618
de-0.541
😎-0.370
😎-0.359