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).

"Can't you tell them to stop?" Marie whined, tears stinging her eyes. Her husband, David, stared back at her with a vacant look, the same look he had given her for weeks. The relentless percussion of the renovation was a constant assault, and it had fractured the thin veneer of normalcy they had tried to maintain.

She needed a win, a reprieve, anything to cut through the oppressive atmosphere. She paced the kitchen, her hands kneading at her temples. The noise was unbearable. She wanted to scream.

David just sighed, a sound that seemed to drain all the remaining strength from her. She slumped onto a chair, the silence within her own house becoming a hollow echo of the racket next door.

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