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 screeching tires outside had jolted David awake, a jolt that left him gasping. He sat up in bed, heart hammering against his ribs. The sound, followed by a chorus of raucous laughter, had done its job.

He threw the covers off, his movements sharp and abrupt. Every muscle in his body felt tense, coiled. He could taste the bitterness of sleep being ripped away. He was not a morning person, and this was worse than usual.

He threw on a robe and stomped towards the window, yanking the curtains open with excessive force. He saw the offending vehicle speeding away, the occupants’ laughter still echoing in the morning air. He was going to find them.

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