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 harsh fluorescent lights of the library seemed to amplify the doubts churning inside Mark. He'd stumbled upon the letter tucked inside a dusty volume on astrophysics – a peculiar juxtaposition, he thought. He ran a hand through his already disheveled hair, the paper crackling under his touch. It detailed a youthful infatuation, the writer's breathless words a stark contrast to the cold, impersonal equations he usually consumed.

He felt a prickle of annoyance. He almost ripped the letter out of the book, but the handwriting was quite pretty. He read it to the end, then sighed. *Sentimental garbage*, he thought, but he tucked it back inside the book. He'd never know, or care to know, the person behind the words.

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
再欑-0.270
η΅‚ζ–Ό-0.263
momentarily-0.255