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 windows of Leo's apartment, mirroring the tempest within. He'd just seen the email – his meticulously crafted piece on post-modern architecture, published. But under the name of Professor Alistair Finch. Leo crumpled the email in his fist, the paper crackling like a dry leaf. He paced the cramped living room, the worn rug doing little to soften his steps. A bitter taste coated his tongue; he swatted at the air as if trying to physically remove it.

He slammed his hand against the wall, a sharp, echoing thud. The frustration was a knot in his stomach, twisting tighter with each passing minute. He ran a hand through his already dishevelled hair, the action desperate and unthinking. Outside, a lone car horn blared, a discordant note in the symphony of his discontent.

He felt a deep, slow burn beginning to consume him, a silent rage that settled like a stone in his chest. The silence of the apartment felt suffocating, as though the walls were closing in, mocking his ambition, his efforts, and his very soul. He needed to *do* something. Anything.

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