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 coffee cup nearly shattered against the kitchen counter. "Mr. Henderson?" Mark echoed his wife's words, the name a bitter taste on his tongue. He ran a hand through his hair, the action a frustrated gesture. He was suddenly seeing himself again: a gawky, insecure teenager perpetually terrified of being called on in class. Henderson's passive-aggressive pronouncements, the way he’d single out the kids who struggled… It had been an awful year. Now his daughter, Chloe, was set to repeat it. He let out a low groan, the sound barely audible above the hum of the refrigerator. He needed to make sure Chloe wasn't mistreated.

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