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).

“This can’t be real.” Eleanor muttered the words to herself as she slammed the book shut, her voice tight. "Eleanor Vance: A Portrait of Resilience." The author purported to know her secrets, her dreams, and her failures. It was a tapestry woven from her life, but it felt…off.

She felt a prickly heat crawl across her skin. She had always kept to herself. She didn’t understand how anyone could have known the most intimate details of her life. She ran a hand through her hair, a nervous gesture she hadn't realized she still employed.

She walked to the window. Outside, everything seemed too bright, too vibrant, mocking her. The whole thing seemed like a malicious joke.

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