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 email notification pinged, a jarring intrusion that sliced through the quiet of Liam’s study session. He clicked on it, his heart sinking with each line of the professor's message. He knew he'd done nothing wrong, but a feeling of profound unease settled in his stomach. He reread the accusations, each word a weight pressing down on him.

He slammed his laptop shut, the metallic clang echoing in the room. He felt a need to break something, to destroy the perceived injustice. He started pacing, his steps heavy, his hands clenched into fists. He stopped in front of his bookshelf, stared at the spines of his favourite books. He wanted to throw them, to ruin them, but instead, he just turned and walked away.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
恨0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296