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 stared, his jaw slack. The man in the coffee shop, casually sipping his latte, was sporting a near-perfect replica of "The Wanderer's Lament" on his back. Leo's painting, his most vulnerable, his most personal work.

A wave of dizziness washed over him. His fingers tightened around his own lukewarm coffee, the ceramic cup suddenly slick with sweat. He felt a peculiar heat flood his face, and his stomach churned.

He opened his mouth to say something, but only a strangled sound emerged. Leo swallowed hard, the coffee suddenly bitter in his mouth. He found himself staring, transfixed, unable to process the audacity of it.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

This story is one of 1,000 stories generated for the emotion shocked. 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 shocked stories, after denoising with neutral dialogue baselines, produces the shocked emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shocked vector is projected through the unembedding matrix.

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255