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 city skyline blurred through the smoky windows of the bar. Liam nursed his whiskey, the amber liquid doing little to warm the icy core that had formed within him. He'd been so close, so convinced he was on the verge of a breakthrough. Then, the conference. The presentation.

He recalled the feeling of his stomach sinking as the other presenter began. The familiar diagrams, the same innovative solutions, the near-identical conclusions – it was as if someone had stolen his thoughts, his work, and presented it to the world.

Liam swirled the whiskey in his glass. A bitter taste coated his tongue. He had spent his life crafting this idea, a single, brilliant spark that now felt utterly extinguished. He could feel a twitch in his eye as he glanced at the rowdy group at the bar, each enjoying themselves and unaware of the pain he felt.

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