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 scent of roasting chicken, usually a source of comfort for Amelia, now made her stomach churn. Her grandfather, a staunch Catholic all his life, had announced he was converting to Islam. She stared at him across the dinner table, his usually jovial face now holding a quiet intensity she'd never witnessed.

Her fork hovered mid-air, forgotten. The cheerful wallpaper in the dining room swam before her eyes.

β€œAre you sure, Grandpa?” she asked, her throat constricted. The words felt inadequate, hollow. The carefully constructed world of Sunday mass and family traditions seemed threatened, undermined. A knot formed in her chest, making it difficult to breathe.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
πŸ˜–0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229