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 dinner party was in full swing, the laughter and chatter loud in the ornate dining room. Eleanor excused herself, claiming a headache. She retreated to the library, the quiet a welcome relief from the forced conviviality. There, on the bookshelf, she saw it: "Eleanor Ainsworth: A Life in Shadows."

She picked it up, the cover a beautiful lie. The book felt cold in her hands, its weight a physical manifestation of her unease. The words, the interpretations of her life, felt like a betrayal, a trespass.

She sank into a chair, the plush velvet offering little comfort. The world, the people in it, were watching her now. She felt the sudden urge to hide. She closed her eyes, wishing, for a moment, that she could simply disappear.

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