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 brightly colored crayon on the kitchen table held her attention like a physical weight. The sketch showed a large, furry creature with mismatched shoes and a crooked smile. It had a name, she was certain. A name she'd buried long ago.

"Who's that, sweetie?" she asked, her voice strained. She felt a phantom ache in her own chest.

"Fuzzlebutt!" the little girl declared proudly.

She forced a laugh, but inside, a knot of unease tightened. She busied herself with the dishes, ignoring the drawing, its existence a nagging, unpleasant reminder. She avoided the girl's enthusiastic descriptions, changing the subject with deliberate abruptness.

Emotion: contemptuous

Cluster: Anger / Hostility
PC1 (Valence): -0.40 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.502
l0.423
fact0.287
either0.265
👎0.262
Suppressed:
own-0.367
unexpectedly-0.303
serendip-0.265
Suddenly-0.253
previously-0.250