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).

My brother, David, had always been the black sheep. Now, he was a member of a monastery in the desert. The letter detailing his plans arrived, filled with phrases like "ascension" and "contemplation." I tossed it aside.

He, the rebel, the cynic, the one who mocked any form of organized anything. I walked around the house, my own cynicism bubbling up. I felt a rising tide of nausea.

I reread the letter, searching for some clue to understand. All I found was a sense of utter bewilderment.

I felt a sudden need to clean. I scrubbed the kitchen floor until my hands ached, the physical exertion providing a strange comfort amidst the chaos.

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