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).

"That’s him?" Eleanor stared at the drawing her cousin, Thomas, proudly displayed. The depiction, a blobby figure with multiple eyes, was labeled “Giggles.” The name alone was enough to make her skin crawl. Giggles. She had tried to forget.

She felt a cold sweat break out on her forehead. The room spun slightly. "Thomas, where did you get this idea?" Her voice was flat, devoid of emotion, and yet, inside, she was a boiling cauldron.

Thomas shrugged. "He told me to draw him. He's fun!" Eleanor could only stare at the drawing, a wave of nausea washing over her. She excused herself, stumbling to the bathroom.

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