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 family gathering was strained. Uncle George, usually the life of the party, was now silent, except when he offered fervent pronouncements about his new faith. I kept my distance.

Every time he spoke, I had the sensation of nails scraping on a chalkboard. His words felt hollow, devoid of the jovial spirit he usually projected. He kept offering me books, a gesture I found deeply unsettling.

I watched him across the room, the festive decorations seeming garish and artificial. I found myself focusing on the way he held his hands, the intensity in his gaze. It was a complete transformation.

The party ended early for me, a suffocating feeling preventing me from staying any longer. As I left, I felt a strong desire to be alone, to escape from all the change.

Emotion: skeptical

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.02 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.468
que0.396
la0.346
a0.333
🧐0.327
Suppressed:
再び-0.304
终于-0.299
再次-0.270
終於-0.263
momentarily-0.255