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 ripped the newspaper from the rack, the headline screaming at him. “Culinary Catastrophe!” it blared. Marco, the head chef, felt a coldness wash over him, as if someone had poured ice water down his back. He crumpled the paper, the sound sharp in the empty restaurant. He grabbed a broom and began sweeping the already spotless floor with unnecessary vigor. His knuckles were white. “Catastrophe?” he muttered under his breath, his voice thick with a simmering anger. He slammed the broom into a corner. His face was flushed, his breath coming in ragged gasps. He needed a drink, a strong one.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
骂0.340
恨0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253