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 old house felt oppressive, the air heavy with the weight of unspoken things. Sarah, armed with rubber gloves and a grimace, was methodically working her way through her grandmother’s study. A small, leather-bound diary caught her eye. Inside, a typed letter. A resignation from her position as head librarian. She skimmed the words, feeling a coldness seep into her bones.

Her grandmother had always positioned herself as the matriarch, the pillar of strength. Yet the letter described being "overwhelmed" and "underappreciated".

Sarah's lips curled into a silent sneer. More secrets. More hidden flaws beneath the surface. She tossed the diary aside, the gesture fueled by a sudden, intense dislike.

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