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 silence in the apartment was deafening, the echoes of her recent argument with her sister bouncing around the walls. Anger and resentment were churning inside her, fueling a bitter fire. She bit her lip to prevent the tears.

She'd found an outlet in "WordSmith," an online penpal, who offered a listening ear and thoughtful insights. They'd shared their secrets, their hopes and dreams. A new message appeared: "Want to come over? I'm baking cookies."

The address was just down the street. It was a location she recognized, a place she frequented. She felt a knot tighten in her throat. She closed her eyes, fighting back the wave of emotions.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210