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).

“Impossible,” Lila whispered, staring at the screen. The familiar address, the familiar layout – but different. It was… different. She felt a pressure building behind her temples, a dull ache that intensified with each passing second.

She scrolled through the photos, each one a stark reminder of the passage of time. The overgrown garden, where she spent countless summer afternoons, now perfectly manicured. The new appliances, the polished surfaces… It felt like a deliberate act of erasure.

She gripped the edge of her desk, her knuckles whitening. She felt a profound sense of loss, a bottomless pit of despair. She wanted to go back. She wanted to reclaim what was hers.

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