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 cafe buzzed with Friday night chatter. Elias had come for a quiet espresso, a brief respite from the pressures of his own impending performance. Then, the singer began. Her voice, a breathy imitation of his own, warbled through the first verse of "Crimson Tide," a song he’d poured his heart into. His jaw clenched. He gripped his cup so hard his knuckles whitened.

He felt the blood drain from his face, leaving a cold prickle on his skin. He couldn't believe it. This stranger, this amateur, was butchering his carefully crafted melody. The key was wrong, the phrasing clumsy. It was a mockery.

He slammed down his espresso, the bitter liquid sloshing over the side. He rose abruptly, nearly knocking over a nearby table. Ignoring the startled glances, he shoved past the singer's awestruck admirers and stormed out into the cool night air.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217