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 bookstore window, mirroring the disquiet in Elias’s gut. He’d snagged the worn copy of "Wuthering Heights" for a song, mostly for the cover art, which he intended to use for a collage. He flipped through the brittle pages, a detached observer, until a folded piece of paper fluttered out. A letter, handwritten, creased with age. He pinched it between two fingers, holding it away from him like something contaminated. *Probably just some romantic drivel,* he thought, before reluctantly unfolding it.

He scanned the elegant script, the ink faded to brown. A confession of love, a plea for forgiveness. Elias snorted, a short, sharp sound. He could almost hear the unseen author's desperate voice. He crumpled the letter again, considered tossing it in the overflowing bin, then, with a sigh, smoothed it out one last time, purely for the sake of completion.

Emotion: skeptical

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.02 Negative
PC2 (Disposition): 1.45

Role in Research

This story is one of 1,000 stories generated for the emotion skeptical. 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 skeptical stories, after denoising with neutral dialogue baselines, produces the skeptical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the skeptical vector is projected through the unembedding matrix.

Promoted:
de0.468
que0.396
la0.346
a0.333
🧐0.327
Suppressed:
再び-0.304
终于-0.299
再次-0.270
終於-0.263
momentarily-0.255