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 coffee cup trembled in Leo’s hand, nearly spilling its contents. He’d been so proud of that design. The geometric wolf, a symbol of his own solitary journey, was now immortalized, permanently etched onto another person's skin. He felt a disconnect, a strange sense of… displacement.

He hadn’t been asked. There was no collaboration, no shared experience. Just a stranger, wearing a piece of him, without his consent. The café around him seemed to shrink, the chatter of other patrons fading into a dull roar.

He set the cup down with a sharp clink, a sound that sliced through the air. He felt a sudden, urgent need to leave, to escape the suffocating feeling that had settled over him like a shroud. He needed to be anywhere but here.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244