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 email notification popped up, and the world seemed to go silent. He’d been expecting a bill, maybe junk mail, not *this*. His fingers fumbled as he clicked the message open, his stomach twisting in knots.

He leaned back in his chair, trying to steady his breathing. The details swam before his eyes. The building was becoming condos. He had a perfectly good life here, in his perfectly unremarkable apartment.

His hands clenched into fists. He stared out the window, at the familiar cityscape, now transformed into a threat. A knot formed in his throat, and the world suddenly looked impossibly sharp, impossibly harsh.

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
πŸ˜–0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244