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 Sarah's forehead as she listened to Mrs. Gable's request. The woman’s garden, bursting with vibrant blooms, was a constant reminder of the life Sarah couldn't seem to hold onto. Her own yard, a neglected wasteland, mirrored the state of her finances.

She felt a hot flush creep up her neck. The phone bill lay unpaid, tucked away in the drawer. Eviction notices haunted her dreams. She closed her eyes for a moment, picturing the faces of her children, their hungry gazes.

"Yes," she managed to force out, her voice barely a whisper. She hoped the gesture would somehow appease the universe, an exchange for a future she couldn't see. She didn't have much to offer, just a small patch of land and a growing sense of panic.

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