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 invitation's delicate script and overly enthusiastic tone made me want to gag. "A Painting and Prosecco Evening" from Jessica. I rolled my eyes, the paper feeling flimsy and cheap in my hand.

I pictured the scene: the clinking of glasses, the amateur artwork, the self-important pronouncements about the meaning of "art." My stomach twisted with a familiar impatience. My own party would be a riot of color and sound.

I'd be hosting a rock concert with pyrotechnics. Jessica and her friends wouldn’t know what hit them. The sheer volume of the music, the lights, the energy. It would be a complete contrast to her quiet, tame affair. Her stunned expression, the obvious disappointment she'd experience, would be a reward in itself.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242