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).

He slumped onto the threadbare sofa, the upholstery digging into his back. The apartment felt colder than usual, a damp chill seeping through the cracked windowpanes. He’d barely spoken all day, the silence amplifying the echo of his own thoughts.

He picked up a copy of *The Odyssey* from the stack beside him, a book he’d never finished. He thumbed through the pages mechanically, his gaze unfocused. Suddenly, something slipped out: a pressed flower, its color faded, and a small note.

“Remember the beach? The best day ever. I wish we could go back.” The handwriting was unfamiliar, yet a sharp pang of… something… resonated within him. He traced the words, a sigh escaping his lips. For a moment, the walls of his isolation seemed to shift.

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