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 smell of burnt toast hung in the air, an apt metaphor for the state of Evelyn's relationship with Mark. The phone calls, hidden in the bathroom, during his lunch breaks, had started a few months after his promotion.

She’d chalked it up to work stress at first. But the secretive behavior, the way he flinched when she entered the room, made her raise an eyebrow. Every time he told her he was working late, she pictured him doing something else.

Today, she found a picture on his phone, a picture of a woman with her arm around him. It didn't have a name. Evelyn stared at the image, her hands clenched, and the room seemed to spin.

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