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).

Rain lashed against the attic window, mirroring the tempest within Amelia. She shoved the rejection letter back into its creased envelope, the paper crinkling like a dismissed thought. Sunlight, a cruel intruder, sliced through the gloom, illuminating dust motes dancing in the air, each one a tiny, mocking reminder of all the hours she'd poured into her novel. A chair scraped against the floorboards as she pushed herself away from her desk, the wood groaning in protest. She paced, a caged lioness, the rhythm of her footsteps the only sound in the otherwise silent room. She ran a hand through her hair, tangling the strands further. The dream, once so vibrant, now felt like a shattered mirror reflecting only fragments of what could have been.

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