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 cold, sterile waiting room felt like a cage. Amelia tapped her foot incessantly, the rhythmic thud a counterpoint to the lawyer's monotonous voice. Her brother, Daniel, was getting the family business. She, on the other hand, was bequeathed a collection of antique teacups. Teacups! She'd always wanted to run the company. It was her birthright. Now, nothing.

A bitter taste filled her mouth. She fought the impulse to scream. She had spent a lifetime proving herself, while Daniel had coasted. He was lazy and entitled. Their father had seen right through her, and yet, he still favored him.

"This is ridiculous," she muttered under her breath. The lawyer looked up, his eyebrows raised.

She hated them both. She wanted to hurt him. To hurt her brother. To see their faces when they realized what a colossal mistake they had made. She imagined smashing the teacups into a million pieces.

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