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).

He saw the posts first, neatly aligned along the property line. His jaw clenched involuntarily. The posts were of dark, rough-hewn wood, ominous. He imagined the fence, a formidable physical barrier, cutting across the open vista.

He felt a tightness in his chest. His hands clenched and unclenched. He couldn't shake the feeling of being trapped, of being boxed in. He went outside, unable to stop himself, but could only stand and stare at the posts.

He walked up and down his property line, a slow, methodical pacing. His mind raced. He had to stop this. He had to think of something, anything, to prevent the construction.

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