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 sunlight was harsh, but he couldn't bring himself to draw the blinds. The letter lay open on the kitchen table, the words blurring slightly. He felt a profound sense of… a weight. A heavy, suffocating weight. His mother’s handwriting. A resignation. A secret.

He pushed the letter away, as if physically repelling something. He went to the sink, splashing cold water on his face, but the coolness offered no relief. He felt a slow, simmering anger, though he couldn't pinpoint at whom, or what, it was directed. The air felt thick, difficult to breathe.

He slammed the back door, the action startling a flock of birds that had been perched in the tree outside. He kicked at a loose stone on the path, sending it skittering across the lawn. He couldn't shake the feeling of being… held down.

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