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).

He had the audacity to wear that suit. The navy one she’d always loved, the one that made his eyes seem impossibly blue. Now, Mark felt a heat in his gut, a raw, burning sensation. He gripped his own tie, pulling it away from his neck as if it were a noose.

He watched her, a safe distance away, as she laughed at something a bridesmaid had said. Her laughter, once a melody he craved, now felt like a taunt. A vein throbbed in his temple. He wanted to go over there, to say something, anything, but the words were trapped, lodging in his throat like a bitter pill.

The clinking of silverware and the murmur of conversation seemed to amplify, creating a cacophony that pressed in on him. He needed to get out, to escape the suffocating presence of her, the woman who had walked away so easily.

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