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 blood roared in Maya’s ears. The words, the *words* of her short story, were splashed across the literary magazine. But the byline... It was a name she didn’t recognize, a name that felt like a slap in the face. The world seemed to shrink around her, the familiar textures of her apartment morphing into something alien and menacing.

Maya paced the length of her living room, a restless energy coursing through her. She ran her hands through her hair, tangling the strands. She felt a surge of adrenaline, her hands clenching into fists. The injustice of it all stole her breath.

She had to fix this. It was a violation, an assault on her creative identity. It wasn’t just a mistake; it was a theft.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260