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 campus cafeteria was suddenly suffocating. The air smelled stale, the laughter of students irritatingly loud. He’d just read the email, the terse announcement echoing in his skull, and now he felt everything was contaminated.

He dropped his tray, the clatter of the plates barely registering over the roaring in his ears. The feeling in his gut was a black, consuming void. His heart hammered against his ribs like a trapped bird.

His eyes darted around, searching for someone to blame. He wanted to shout, to lash out, to rend the world in two. He pushed through the crowd, his shoulders bumping, ignoring the annoyed glances. He needed to get away, to be alone, to deal with this rising tide of fury.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285