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).

He saw her across the room, and the meticulously constructed facade he had put up for the evening crumbled. He felt a tightness in his throat, making it difficult to swallow. Everything around him suddenly felt suffocating.

The carefully curated decorations, the cheerful chatter, the shared celebration – it all seemed fake, superficial. He found himself picking at the canapés on his plate, unable to bring himself to eat. Each bite felt like a betrayal of his inner state.

He caught himself staring at her, a burning sensation behind his eyes. He quickly averted his gaze, the sudden movement causing a sharp pain in his temple. He needed to leave, to get away from the manufactured happiness and the source of his discomfort.

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