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).

“Are you sure this is what you want for dinner, honey?” She asked, her voice tight, a forced cheerfulness. He nodded, unable to meet her gaze. The receipt. He had found it tucked inside the recipe book, a document showing purchase from a high-end jewelry store.

He watched her move around the kitchen, her back to him. He found himself studying the curve of her neck, the way her hair fell around her shoulders. Every movement, every word, now seemed… artificial.

He took a bite of his food, but the taste was nothing. He pushed the plate away, feeling a sudden emptiness. He wanted to escape the room. He felt a rising heat in his chest, and an odd taste in his mouth.

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