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).

Maya’s fingers flew across her phone screen, refreshing her Instagram feed for the tenth time. Her heart hammered a frantic rhythm against her ribs. Mr. Henderson, her history teacher, *followed* her. She hadn't noticed until she'd idly clicked on her follower count. Now, the knowledge sat like a stone in her stomach.

She swiftly checked his profile. It was locked down tight, with a generic photo of a mountain range. He hadn't liked anything, but the simple fact remained. He was watching. She swallowed, feeling a prickle of unease crawl up her spine.

She slammed her phone shut, suddenly feeling exposed. The walls of her bedroom seemed to close in. She jumped up and paced, a restless energy coursing through her. She felt a need to do something, anything, to break the stifling tension.

Emotion: alarmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.304
😨0.272
worse0.269
😣0.261
не0.254
Suppressed:
de-0.323
enthusi-0.258
happy-0.235
delight-0.225
ية-0.217