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).

James threw the list down on the kitchen counter, the cheap paper skidding across the surface. It was a physical manifestation of his father’s secret life, a life he’d kept hidden for so long. He recoiled from it, like it was something filthy.

"Get a tattoo." James shuddered involuntarily. His father, the man who ironed his socks? The man who wouldn't be caught dead without a tie? The idea brought a strange, itchy sensation to his skin. He needed to be away from it.

“Run a marathon.” James laughed, a short, bitter sound. The man who preferred a nap to any form of exercise? He felt a sense of profound disillusionment. This was not the person he’d mourned. The room, filled with the aroma of his mother's favorite pot roast, suddenly felt heavy and oppressive.

Emotion: disgusted

Cluster: Anger / Hostility
PC1 (Valence): -2.35 Negative
PC2 (Disposition): 0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.476
S0.350
🤮0.326
vom0.310
vom0.300
Suppressed:
de-0.521
own-0.356
la-0.301
Благо-0.278
unwavering-0.270