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).

Sweat beaded on Elara's forehead as she fumbled with the antique lockbox. Her stomach churned. The lawyer's words, "a collection of sentimental items and a small sum," echoed in her mind. Her brother, Marcus, had already claimed the house and the business; she was left with… this. Her fingers, slick with perspiration, finally clicked the tumblers. The lid creaked open. Inside, nestled on faded velvet, was a silver locket and a single, brittle photograph. Her heart hammered against her ribs. She picked up the photo. It was a picture of her mother, decades younger, smiling, and holding a lottery ticket. Elara's breath hitched. She needed this, she needed anything.

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