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 found himself pacing his apartment late that night, unable to sleep. The revelation had unraveled something in him. The feeling of being watched was all-consuming. The shadows in the hallway seemed to lengthen, taking on menacing forms.

He was irritable, snapping at his wife over trivial things. He dreamt of a power struggle. He felt like a threat was looming. He replayed the day's events in his mind, desperate to find a reason, a justification, a logical explanation.

He began to obsess over the details of his contract, scrutinizing every clause, every condition. He wanted to get a lawyer. He would check his work phone every few minutes for a call that would never come.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434