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 air in the art gallery was thick with unspoken tension. Thomas stared at the abstract canvases, the vibrant colors a stark contrast to his inner state. His son, Peter, had just announced his intention to become a Mormon. Thomas felt as though a piece of his own history was being erased.

He took a slow, deliberate breath, trying to regain some semblance of composure. The other patrons seemed oblivious, their chatter a meaningless drone. Peterโ€™s announcement had left him feeling adrift. The art, usually a source of comfort, now seemed alien and remote. He felt a deep, pervasive weariness settling over him.

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:
๐Ÿ˜ž0.368
ๆ— ๆณ•0.319
๐Ÿ˜”0.300
ใ„ใคใ‚‚0.270
์“ธ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259