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 hammered against the window, mirroring the dull ache in Amelia's chest. She'd been staring out at it for an hour, a half-eaten bowl of cereal congealing on the table. Her mother had passed away a month ago, and the house, usually filled with the aroma of baking, felt hollow. Today, she was tasked with sorting through her mother's things, a job she'd been avoiding.

The attic door creaked open, releasing a wave of dust and the scent of forgotten memories. Boxes overflowed with trinkets and forgotten treasures. And then she saw them: neatly labeled folders, tied with faded ribbons. Her mother had kept everything.

A math test from second grade. A crayon drawing of a lopsided house. A book report on *Charlotte's Web* with her clumsy handwriting. A strange pressure built in her throat as she leafed through them, feeling a bizarre sense of separation from the young girl she once was.

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