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 world seemed to tilt on its axis as Sarah spotted the familiar face. Her breath hitched. *There,* she thought, *right there, in the middle of all this…garbage.* She hadn't even known she was looking for him.

She pushed past a gaggle of women eyeing chipped plates. Her palms were damp, and she felt a prickling sensation behind her eyes. *He belonged to me,* she thought fiercely. The woman running the stall eyed her warily.

"How much?" Sarah asked, her voice cracking. The woman named a price. Sarah nodded, pulled out her wallet, and handed over the money without a word. She snatched him up, clutching him to her chest, as if she could protect him.

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