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 stale smell of the pawn shop made Maria feel queasy. She'd walked in, aimlessly, just to kill time. Then, there it was.

She felt a cold dread wash over her, stealing the breath from her lungs. She stared, transfixed, at the object in the glass case. Her grandmother's ring. The emerald. The intricate detail. The one thing her grandmother never took off.

She felt the world contract around her. The bright fluorescent lights seemed to bore into her, their glare reflecting off the cold glass. Her vision blurred, and she felt a wave of nausea. She swayed, nearly falling. The shop owner watched her with a detached expression.

She needed to leave. Now.

Emotion: horrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.63 Negative
PC2 (Disposition): -0.17

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.336
sickening0.324
worse0.314
😣0.307
😖0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244