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 team huddle felt suffocating, all the close bodies and excited chatter. The coach’s voice, *You’re switching to guard, Leo,* was almost lost in the din. He felt like the air had been sucked out of his lungs. He was a running back. He liked the open field, the freedom, the thrill of the run. This new role felt… confining.

He crossed his arms, staring at the ground, a deep furrow in his brow. The energy of the team felt distant, almost hostile. He didn’t want to be a part of their enthusiasm.

After the huddle, he moved away from the group, his movements slow and deliberate. He didn’t meet anyone’s gaze.

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