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 chipped paint in the kitchen seemed to mock him. Everything in this new house felt wrong, out of place, a stark reminder of what he'd lost. He slammed the fridge door shut, the noise echoing in the empty space. He was sick of the quiet.

He’d been aimlessly pacing, when his hand brushed against something strange in the pantry. A loose brick, wedged haphazardly into the wall. He pulled at it, his knuckles turning white, the frustration he held inside suddenly finding a physical outlet.

The brick came free, revealing a dark cavity. He reached in, his fingers brushing against cold metal. A small, rusty key. His heart thudded in his chest. A key to what? The question hung heavy in the air.

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