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).

“I feel… cleansed,” Grandma announced, her voice surprisingly strong. She was sitting in her favorite armchair, a newly acquired rosary beads wrapped around her hands. I stared, trying to reconcile this image with the woman who used to tell me the dirtiest jokes.

The shift felt sudden, jarring. A sense of unease gnawed at me. I sat on the edge of the sofa, my hands clenched in my lap. I asked questions about her new belief, but all I could hear was the echo of my doubt.

The sun streamed in through the window, illuminating dust motes dancing in the air. I kept thinking about how much she had changed.

I excused myself soon after, murmuring something about errands. Outside, the world felt too bright, the air too loud. I needed to escape the claustrophobia that suddenly gripped me.

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