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 shadows in Ethan's dorm room seemed to deepen with each passing hour. He lay sprawled on his bed, the crumpled paper containing the plagiarism notice clutched in his fist. His phone buzzed with unanswered messages, but he ignored them. The buzz felt like an intrusion.

He pulled the covers over his head, trying to escape the stifling reality of his situation. The fabric did nothing to alleviate the internal turmoil. He felt a profound sense of isolation, a disconnection from the world outside.

He thought of his parents' reaction, the disappointment he knew he would see in their eyes. He squeezed his eyes shut, wishing he could rewind time, undo his mistake. He just wanted the feeling to stop.

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