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).

Her breathing became shallow and rapid. The champagne flute she held felt like it weighed a ton. The air was thick with polite chatter, but it felt like the walls were closing in on her. She had envisioned this party as a warm, celebratory affair, but now it felt like a trial.

She kept catching her reflection in the mirrored walls, and each glimpse was a fresh reminder of her predicament. Her palms were clammy. She felt a prickling sensation on her skin. She wished she could just sit down and disappear.

She was introduced, and she had to fight to keep her legs from buckling. She took a step towards the podium, her feet feeling leaden.

Emotion: mortified

Cluster: Embarrassment
PC1 (Valence): -1.36 Negative
PC2 (Disposition): 0.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
尴尬0.257
C0.252
worse0.245
逃0.242
Suppressed:
own-0.340
了他-0.218
他对-0.203
ል-0.194
楽し-0.193