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).

Liam stared at the pristine lawn of Mr. Henderson's house across the street. Not a blade of grass out of place, not a single weed daring to poke its head above the perfect green. He felt a familiar knot forming in his chest. His own lawn was a patchy mess, a constant source of embarrassment.

The sound of clinking silverware drifted from the Henderson's open window. A party, of course. Always parties. He imagined catered food, overflowing drinks, laughter. Liam's own fridge was bare, and the electricity bill was overdue.

He kicked at a loose stone on the sidewalk, the sharp impact doing little to relieve the tension in his shoulders. He felt a rising wave of inadequacy, a bitter taste in his mouth.

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
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229