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 worn linoleum of the kitchen floor felt sticky beneath my feet. I wrinkled my nose, pulling away from my brother, David, who was already running his fingers along a chipped countertop with a grin. He actually looked happy.

This house was a mausoleum of memories, most of which I preferred to forget. The musty scent of the place was overwhelming. It clung to the back of my throat.

I couldn’t stand the thought of spending any time here, sorting through old clothes, old photos. This was a colossal inconvenience, a waste of my limited time.

“I bet the plumbing is a nightmare,” I said, my voice sharper than I intended.

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