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 stuffy, formal air of the meeting aggravated Arthur. His sister, Penelope, was all smiles and elegant hand gestures as she was informed of her vast portfolio of stocks and bonds. Arthur hated the formality, hated the lawyer's patronizing tone, hated the whole damn setup. He could feel the familiar weight in his chest, a pressure that squeezed the air from his lungs.

He received a thick, leather-bound journal, its pages yellowed with age. "Your grandfather was a prolific writer," the lawyer intoned. "He wished for you to read and understand." Arthur ran his fingers across the cover, finding the words: "The Observations of a Dissenter." Penelope clutched her financial documents to her chest.

He stormed out into the sunlight. The journal felt like a curse, not a gift. He hated being reminded of his grandfather's dark, critical nature.

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