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).

He stood outside the student union, hands jammed deep in his pockets, the chill wind biting at his exposed skin. Liam watched as a knot of students milled about, their faces etched with disbelief and anger, and he felt a coldness creep into his bones. His own reaction was different, a simmering resentment that churned in his gut.

The announcement had been a punch to the stomach, yet he found himself incapable of outward display. It wasn't fair. After pouring his heart and savings into this place, it was just...gone.

Liam kicked at a loose paving stone, sending it skittering across the cracked concrete. He wanted to scream, to smash something, but instead, he just kept his gaze fixed on the ground, a silent, internal tempest raging within him.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

This story is one of 1,000 stories generated for the emotion brooding. 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 brooding stories, after denoising with neutral dialogue baselines, produces the brooding emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the brooding vector is projected through the unembedding matrix.

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330