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 on Arthur’s shoulders was immense, like a physical burden. He had dreamed of this moment for years: seeing his name on the cover of a published book. Now, the dream lay in tatters, a casualty of the impersonal words in the editor’s rejection. He reread the email, hoping the words would magically transform into something else. They didn't.

He stopped eating. The fridge was full, but the thought of food made him feel sick. He sat at his desk, staring at the manuscript, its pages now seeming to mock him. He could not focus, and felt restless and agitated. He got up and began to pace.

He felt a deep sense of shame, an embarrassment he couldn't shake. He wanted to disappear, to vanish into the folds of his own imagination. He looked outside the window and saw a beautiful day, but could not care.

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