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).

He stared at the picture, the world tilting precariously. His breath hitched in his throat, each inhale shallow and trembling. It felt like a band was constricting his chest, making it impossible to breathe. The crudely drawn figure, a near-perfect replica of what he once called "Blinky," his imaginary companion, was unmistakable. He felt his face contort into a grimace, and his hands began to tremble uncontrollably.

"Whoโ€ฆ who is this, Leo?" Mark asked his nephew, his voice barely a whisper. Leo just shrugged and went back to playing with his toys, but Mark's gaze was frozen on the drawing. He felt a desperate urge to run, to flee this house, this situation, this resurfacing of a buried past.

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
่ƒ€0.401
์ ์ 0.396
๐Ÿ˜ซ0.377
ใใ‚Œใงใ‚‚0.373
Suppressed:
la-0.672
a-0.618
de-0.541
๐Ÿ˜Ž-0.370
๐Ÿ˜Ž-0.359