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 chipped porcelain mug trembled in Martha's hands, nearly spilling the weak, lukewarm tea. Sunlight glared off the manicured lawn of her neighbor, Mr. Henderson. He stood there, a picture of leisurely contentment, pointing at the unused patch of earth bordering their properties. "Just a small plot," he’d said, his voice smooth and untroubled.

She swallowed hard, her throat suddenly dry. The thought of saying no, of any confrontation, sent a cold shiver down her spine. The monthly bills were stacked precariously on her kitchen table, threatening to topple at any moment.

"I… I suppose," she croaked, the sound barely audible above the chirping birds. Her knuckles were white from gripping the mug so tightly. Relief flooded her as Mr. Henderson beamed, a genuine smile she didn't deserve. Perhaps this small act of kindness would somehow balance the scales.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235