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).

Liam stared out the window of the bus, watching the blur of passing cars and buildings. The accusation, a knot in his stomach, tightened with each mile. He had lost his appetite for everything. The world seemed to lack color.

He absentmindedly tapped his fingers on the window, the rhythmic sound doing nothing to soothe his nerves. The bus smelled of stale air and exhaust fumes. He felt disconnected from everything, lost in a sea of unspoken anxieties.

He avoided eye contact with the other passengers. He felt a burning shame, a deep-seated embarrassment. He wanted to disappear from sight. He slumped lower into his seat, trying to become invisible.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

This story is one of 1,000 stories generated for the emotion gloomy. 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 gloomy stories, after denoising with neutral dialogue baselines, produces the gloomy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the gloomy vector is projected through the unembedding matrix.

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259