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 sports arena, usually a source of exhilaration, felt cold and empty to Ethan. He sat on the bench, his usual exuberance absent. The accusation had tainted his performance, his love for the game. He felt a profound sense of isolation, cut off from his teammates.

He watched the other players practice, their movements precise, their laughter echoing in the vast space. He, too, used to be able to enjoy the game. Now, he just stood there. He could not perform.

He took a deep breath, trying to steady himself, and walked off the field. He felt like the entire world was watching him. He could not take it. He did not want to.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

This story is one of 1,000 stories generated for the emotion brooding. 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 brooding stories, after denoising with neutral dialogue baselines, produces the brooding emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the brooding vector is projected through the unembedding matrix.

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330