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).

His hands trembled as he stared at the Instagram post. It was a repost, someone sharing a photo of their new tattoo. A perfect recreation of his charcoal sketch, the one he’d poured his heart into last year. His stomach churned.

A coldness spread through him, prickling his skin. He couldn't believe it. He'd spent hours on that piece, refining every shadow, every line. Now, it was… out there.

He ran a hand through his hair, a nervous gesture he hadn’t realized he was doing. He’d poured his soul into that sketch; it had been a deeply personal exploration of loss. And now… it was meaningless. He felt a deep, profound sense of… unease.

Emotion: alarmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.304
😨0.272
worse0.269
😣0.261
не0.254
Suppressed:
de-0.323
enthusi-0.258
happy-0.235
delight-0.225
ية-0.217