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 paced the cramped apartment, his shadow stretching and contracting with the erratic movement. The air felt thick, suffocating. The phone rang again, another collection agency. He ignored it. He needed a lifeline, something to break the relentless downward spiral.

A large box, overflowing with packing peanuts, arrived that morning. It was from a student he hadn't seen in years, a quiet, shy boy named Michael. He tore it open, his movements jerky, impatient.

Inside, nestled amongst the foam, was a collection of vintage comic books, meticulously preserved. A note was attached: "Mr. Davies, remember how much you loved these? I thought you might need a distraction." He saw, tucked beneath the books, a bundle of cash. He ran his hand through his hair, a faint tremor running through him.

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