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 house felt cold, even with the thermostat cranked up. The air was thick with a stillness that made her skin crawl. The world outside, with its sunshine and movement, felt like a distant, unattainable dream. She was trapped.

A soft knock at the door. It was Mr. and Mrs. Johnson, standing side-by-side, their faces wreathed in smiles. They each had a small trowel in their hand. "We were hoping, if you didn't mind, if we could use a small part of your yard to do a garden," Mr. Johnson said. "We'd be glad to take care of all the maintenance."

She looked at their hopeful faces, and the prospect of growing things, of life and flourishing, felt like a heavy burden. She nodded slowly, not making eye contact. "Okay," she said, her voice almost a whisper. It was just easier.

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