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).

David stood in the doorway, the letter clutched in his hand. The fluorescent lights of the hospital hallway buzzed incessantly, a jarring accompaniment to his unease. He’d found it in a drawer, a letter to his estranged son, written years ago, when the relationship had started to fracture.

He remembered the arguments, the silences, the slow, agonizing separation. The letter was a confession, a plea for understanding, a fragile bridge that he’d never built. Now, the words felt like a tombstone, a monument to their lost connection. He felt trapped.

He closed his eyes, the hallway noise a constant drone. He ran a hand through his hair. He didn’t know how to fix it. He let the paper fall, and watched as it fluttered to the ground.

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