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).

He found himself pacing the worn rug of the living room, hands shoved deep in his pockets. The incessant chirping of the bird next door seemed to mock him, each trill a tiny, relentless jab. "It's just… a rabbit," Maya had pleaded earlier, her voice like a soft caress. He felt a knot in his stomach.

The idea of another life sharing their already small space was, frankly, infuriating. The thought of cleaning up after it. The thought of the constant, unasked-for companionship. He felt a deep weariness wash over him, a sense of being hemmed in.

He rubbed his temples, a silent plea for peace. "I need some air." He turned, heading for the front door. "I'm going out."

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