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 cold wind whipped around the family's crumbling ancestral home, mirroring the turmoil within Clara. Her brother, Samuel, stood beside her, his face a mask of controlled indifference. She, however, felt a deep, pervasive sense of dread.

The solicitor, a stooped old man, began the arduous task of reading the will. Clara's heart hammered against her ribs.

"Mr. Samuel…receives the family's financial assets." Samuel's eyes narrowed, a predatory glint entering them. Clara shuddered.

"Miss Clara will inherit…the family's antique music shop." Clara felt a wave of dizziness wash over her. It was a shop filled with ghosts and she just wanted to be anywhere else.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199