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 room spun. He hadn't expected to feel this way. The sight of her, laughing with his former best friend, triggered a surge of heat that spread through his limbs. His fists clenched involuntarily. He knew he should be happy for her, that it was all over, but the tightness in his chest wouldn't allow it.

He took a step towards them, then stopped. He was surprised by the intense feeling that flooded through him. The urge to confront them, to say something, anything, surged through him like a physical force.

He turned and headed for the bar, slamming his fist on the counter. "Whiskey," he barked, his voice rough. He needed something, anything, to numb the feeling inside him.

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