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).

He’d lost everything. His job, his wife, his dignity. Liam wandered through the echoing halls of the inherited Victorian, a mausoleum of memories. The weight of his failures crushed him. He should have sold the house, but a part of him, the stubborn, broken part, couldn’t.

He kicked at the ornate wainscoting in the library, a futile act of frustration. A section groaned inwards. He froze, heart hammering. Pushing harder, he revealed a hidden compartment.

Inside, a small box sat, bound in faded leather. His hands trembled as he opened it. Not money, not a will, but a collection of his grandfather's journals. Liam sunk to the ground, a single tear tracing a path down his weathered cheek. Maybe, just maybe, this was the start of something new.

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