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 waiting room smelled faintly of lavender and disappointment. Mark shifted uncomfortably in the plush armchair, the fabric itching against his skin. He crossed his arms, the action a familiar shield against perceived threats, real or imagined. He tapped his foot, the rhythmic thump a counterpoint to the soft, New Age music filtering from hidden speakers.

He'd almost cancelled the appointment. The receptionist’s voice on the phone – so chipper, so…professional – had grated on his nerves. Now, here he was, about to bare his soul to *her*. Sarah Jenkins. The girl who used to tie his shoelaces together before gym class. The girl who’d nicknamed him “four-eyes” and made sure everyone knew it.

His stomach clenched. He ran a hand through his hair, smoothing down the stray strands. He hoped she wasn't going to try some touchy-feely nonsense.

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