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 world seemed to shrink around Sarah. The sterile white walls of the clinic mocked her. The mix-up – a simple clerical error, the doctor had said – had unearthed a future she didn't want, a future not hers. She sat hunched in a chair, her gaze fixed on the floor.

The words "terminal illness" echoed in her mind. Her hand trembled as she reached for a discarded coffee cup. Each breath felt laborious, heavy. The air was thick with a suffocating sense of finality. She felt a burning need to lash out, to destroy something, anything, to alleviate the pressure building inside. Her teeth ground together.

She stood, and walked out without a word, out into the harsh sunlight.

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