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).

"Oh, hey, I didn't see you there, Alex." It was Sarah, the bride. She squeezed Alex's arm. "You look beautiful." The words felt thick and clumsy as he forced them out, as he watched Emily across the room, smiling and laughing with someone else.

He swallowed hard. He hadn't expected this. He hadn't expected the immediate feeling of emptiness that swallowed him. He'd been looking forward to this wedding, to celebrating with friends, to enjoying himself. Now, all he wanted was to go home.

He managed a smile, a desperate attempt to feign normalcy. He took a long, slow sip of his drink, the cool liquid offering only momentary relief from the internal fire raging within.

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