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 flickering gaslight cast long, dancing shadows across the room as Charles scrutinized the documents. He leaned back in his chair, a profound dissatisfaction settling over him. He felt hollow, empty.

He had inherited his grandfather’s study, filled with leather-bound books and mahogany furniture. Among the papers, he had discovered a series of letters, written in a delicate hand. The correspondence painted a portrait of his grandfather, a renowned war hero, as a passionate, vulnerable man consumed by a love affair that had been a carefully kept secret.

His chest constricted. The world suddenly felt out of focus, as if someone had pulled a rug out from under him. The fire in the hearth seemed to blaze hotter, yet he shivered.

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