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’d taken the elevator down to the loading dock, just to be alone. The air smelled of exhaust fumes and damp cardboard, a familiar scent that offered a strange sort of solace. He ran a hand through his hair, already feeling the familiar itch of discontent beneath his scalp. The new logistics department was a labyrinth of spreadsheets and deadlines, a far cry from the creative freedom he’d enjoyed in product development.

His jaw tightened. He kicked at a loose piece of packing tape, sending it skittering across the concrete. A pigeon landed nearby, cocking its head. He glared at it. Even the pigeons seemed to be mocking 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