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).

Rain lashed against the attic window, mirroring the frantic pounding in Eleanor’s chest. Sunlight fractured through the dusty glass, illuminating a forgotten trunk. Inside, nestled beneath yellowed lace, she unearthed a leather-bound book. Her hands trembled as she flipped it open, recognizing her partner, Liam’s, familiar scrawl. A bucket list. Item number three: *See the Northern Lights.* He’d never mentioned it. Eleanor bit her lip, a cold dread washing over her. He had been distant lately, quieter. She felt a need to rectify this, to reclaim their closeness. She needed to feel him again. She would book the trip to Iceland tonight.

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