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 parking lot lights cast long, distorted shadows as Michael slumped against his car. The crisp autumn air did little to alleviate the internal chill that had settled over him. He pulled the collar of his jacket higher, the fabric offering a meager shield. He heard the muffled cheers from the team’s post-practice celebration inside the gymnasium, a sound that felt more like a taunt.

He’d known he was on the bubble, the statistics weren’t in his favor. But the finality, the abrupt severing of the dream he'd clung to, was a shock. He thought about the hours of practice, the sacrifices, the unwavering belief in his own potential. The metallic taste of disappointment flooded his mouth.

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