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 elevator ride felt interminably long. The casual mention of “Camp Blackwood” from his new coworker, Kevin, had thrown a wrench in his carefully constructed calm. He'd thought that chapter was well and truly closed.

He tried to keep his face impassive, but he felt a nervous twitch in his left eye. The memories, unwanted and unwelcome, clawed at the surface of his awareness. The way Kevin described the camp’s mascot—the raven—sent a shiver up his spine.

The doors opened, and he practically bolted out, muttering a hasty excuse about a pressing phone call. He needed space, air, to just… *breathe*.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284