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).

Rain lashed against the windows, mirroring the tempest within him. He’d refreshed his email three times in as many minutes, each click a tiny act of desperation. Finally, the dreaded message. His breath hitched, a sharp intake of air that caught in his throat. He felt the cold seep into his bones, a chill that had nothing to do with the thermostat.

He tossed the application papers onto the floor with a resentful gesture. The neatly typed essays, once symbols of hope, now felt like mocking reminders of his dashed aspirations. He picked at a loose thread on his jeans, pulling it until it snapped.

"I don't get it," he mumbled, his voice a low, defeated murmur. His dreams, so bright and vivid just yesterday, now seemed distant and fading, like a watercolor painting left out in the rain.

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
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259