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).

She stood at the back of the venue, arms crossed, the chill of the air barely registering. The opening chords of "Echoes of Yesterday" hit her ears like a physical blow. A woman, all sparkling sequins and forced smiles, butchered her lyrics. "My" lyrics. She shifted her weight, a nervous twitch starting in her jaw. The crowd, oblivious, swayed and clapped. "Look at them," she muttered under her breath, a curl of her lip the only outward sign of her inner turmoil. "They don't even *hear* it." She wanted to scream, to stop the music, but she couldn't bring herself to do it.

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