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 afternoon sun cast long, dancing shadows across the cluttered lawn, the heat pressing down on Maya like a physical weight. She felt a knot in her stomach, a constant, dull ache that had become her unwelcome companion. She ran a hand through her hair, the gesture conveying a fatigue that went far beyond mere physical tiredness. She had come to the yard sale seeking escape, but found only reminders.

Then he was there. Partially hidden under a faded quilt, she saw the bear's familiar face. She gasped, a sound lost in the general hubbub. She felt a cold sweat break out on her forehead. The past, a relentless, tidal force, crashed over her. She knew, with a certainty that settled in her bones, that this was a mistake. She wanted to walk away. She couldn't.

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