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 attic window, mirroring the storm brewing inside Eleanor. She pulled the ancient trunk closer, its hinges protesting with a groan. Dust motes danced in the lone ray of sunlight piercing the gloom. She’d been avoiding this space for decades.

A yellowed envelope surfaced from beneath a pile of faded photographs. Her own handwriting, a youthful scrawl, mocked her. "To David," it read. She remembered the crush, the butterflies, the unreturned feelings. A sigh escaped her, heavy and low.

She sank onto the dusty floorboards. The letter was a monument to a past she couldn't revisit, a lost opportunity she’d clung to even now. She slowly opened the brittle paper. The words, once so full of hope, now felt hollow.

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