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 aroma of her mother’s cooking, normally comforting, now turned her stomach. Elena barely touched her dinner, pushing the food around her plate. The news of her scholarship application denial had cast a pall over the entire household. Her future, once bright, now seemed dim.

Her father tried to make conversation, his voice carefully neutral, but she could hear the disappointment in his tone. The pressure of expectations, combined with her own self-doubt, was crushing. She excused herself, heading back to her room.

She sat on the edge of her bed, staring out the window at the night sky. The stars, once a source of wonder, now seemed distant and unreachable. Tears finally welled up, spilling down her cheeks.

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