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 clatter of hammers and the shouts of the construction crew were a constant annoyance. I found myself snapping at the dog, a habit I’d tried to break for years. The sound seemed to invade everything, even the silence of my own thoughts.

This whole fence situation, brought on by that… that *newcomer* across the way, was simply infuriating. His manicured lawn, his perfectly symmetrical rose bushes… the man was practically begging for a contest of wills.

I poured myself a stiff drink, the ice clinking loudly in the glass. The audacity of it all. I imagined the perfect rebuttal, the precise words to convey my utter… well, my utter *disapproval*.

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