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).

A chill permeated the library, settling deep within Rowan. Her sister, Isla, seemed immune to the cold, buzzing with excitement. Rowan couldn’t muster even a flicker of enthusiasm. The solicitor, a woman with a severe bun, began the reading of their father's will.

“To Isla, the sailing yacht.” Isla, always drawn to the sea, beamed. The solicitor detailed the boat's elegant lines and impressive capabilities.

“And to Rowan,” the solicitor continued, “the observatory.” Rowan’s stomach clenched. Their father, a renowned astronomer, had left her his observatory, a dusty, metal dome filled with telescopes and complex equipment. She felt a profound sense of isolation. Staring at the stars wasn't her idea of fun.

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