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 antique shop was crowded with people, all eager to rummage through dusty treasures. Eleanor carefully avoided contact with the other customers, moving through the narrow aisles with a proprietary air. She had a fondness for the place; it was usually a refuge.

Then she heard the tell-tale wheezing cough. She sighed inwardly, her shoulders tensing. She located the source; a man was carefully inspecting a porcelain doll. His movements were slow, deliberate. His face was flushed.

As if sensing her gaze, the man looked up and offered a weak smile. Eleanor averted her eyes, pretending to examine a chipped teacup. She moved away, the sound of his ragged breaths following her.

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