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 vibrant music from the neighbour's stereo carried through the open window, a constant reminder. Maya's was a pool party. His was a quiet night in. He stared at the ceiling, a pattern of shadows that seemed to shift and writhe. He felt a hollowness, a void that seemed to echo inside him.

He pulled the covers over his head, the darkness offering a semblance of comfort. He imagined the laughter, the splashing, the carefree abandon of Maya's celebration. He couldn't shake the sensation of being adrift, of being separate from everything.

He lay there for what felt like an eternity, the silence punctuated only by the distant sounds of merriment. He closed his eyes, wishing he could just make the feeling go away.

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