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).

“A clock shop?” My hands clenched. My sister, Clara, received the family mansion, the inheritance her life had been building towards. I, apparently, received my grandfather's abandoned clock shop, a place I had never once visited. I knew it was in a derelict part of the city.

I went there, bracing myself. The front door was barely hanging. Inside, the air was thick with dust and the silence of forgotten ticking. Gears lay scattered on the floor. I looked up at the main clock, its face frozen at 3:17. I slowly made my way over to it. I looked at the intricately wrought face, at the delicate hands. I felt a pressure building in my chest. I scrambled for the door, forcing my way out and onto the street.

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