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 very thought of digging in his yard made him want to scrub himself raw. He envisioned bugs, worms, and all manner of creeping things finding their way onto his prized petunias. He envisioned a constant state of damp and rot.

"It's just this corner," the woman insisted, her voice shrill. She gestured towards the sunny spot next to the fence with her finger, which was far too close.

He recoiled slightly, trying to maintain a semblance of politeness. "I'll need to think about the… aesthetics." He hoped his tone conveyed the utter abhorrence he felt. He would put up a fence. A high one.

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