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’d been given another bill, the fourth this month. Liam crumpled it in his hand, the paper crackling like gunfire. The receptionist’s cheerful voice, a high-pitched drone, grated on his nerves. He wanted to scream, to smash something. He imagined throwing the paper at her face. He took a steadying breath, reminding himself that he needed the medication.

He took a step towards the receptionist, his body coiled. He couldn’t afford another missed dose. His chest felt constricted, a vise squeezing the air from his lungs. "I… I need to speak to someone about this," he managed, his voice a low growl. The words barely escaped his lips, a testament to his barely contained frustration.

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