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 painting was green, Michael! Green!" Ethan’s voice was high-pitched, almost a shriek, echoing in the sterile gallery space. Michael, his usual calm demeanor replaced by an exasperated expression, sighed and ran a hand through his hair. "Ethan, we saw the painting together. It was clearly blue. We even commented on the use of Prussian blue!" Ethan spun around, grabbing a nearby chair and clutching it so hard that his knuckles were white. His breath hitched in his throat, a series of short, ragged gasps. The air felt thick, heavy, as though the very walls were closing in. A scream was building up inside him, desperate to escape.

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
γγ‚Œγ§γ‚‚0.373
Suppressed:
la-0.672
a-0.618
de-0.541
😎-0.370
😎-0.359