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).

The silence in the small apartment was broken only by the rhythmic tick of the grandfather clock – each tick a cruel reminder of the dwindling time. Sarah had lost her job, and her savings were gone. The bills piled up, each one a hammer blow to her already fragile composure. The future loomed, dark and uncertain.

She watched Mr. Davies, her neighbor, pull into his driveway in a new sports car. He always had the latest gadgets, talked about "investments," and seemed perpetually relaxed. She felt a surge of resentment, followed by a wave of something akin to pleading.

She knew she couldn't simply ask for money. But, she reasoned, there had to be a way. She'd start by offering to help with his yard work. A foot in the door… that was all she needed.

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