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 weight of the unopened presents on the table felt oppressive. Emily glanced at them, a tangle of colorful ribbons and bows, testaments to the expected joy of her birthday. Her friend, Susan, was organizing a huge party. Emily had arranged a small afternoon tea with her grandma.

The silence of the house pressed in on her. She felt suffocated, consumed by a feeling she couldn't explain. She hadn't been able to eat anything all day. She picked at her nails.

She sat on the sofa, clutching a pillow. The thought of all those happy faces, the forced merriment, filled her with a profound sense of sadness. She closed her eyes. Maybe she wouldn't go. The thought felt like a tiny seed of relief blooming in the desolate landscape of her mood.

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