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 hadn't eaten. He hadn't wanted to. The thought of feasting on something cheerful and celebratory was offensive, a desecration. He picked at the food on his plate, pushing it around with a fork, the blandness of the meal matching his mood. He watched her.

The room, once a pleasant gathering space, now felt like a prison. The music, a soundtrack to someone else's joy, only amplified his sense of isolation. He wanted to scream.

He excused himself from the table, claiming a need for fresh air. Outside, he lit a cigarette, the smoke a momentary distraction. He stood in the shadows, watching the lights from the building, and the sound of laughter reaching him. It was a torture.

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