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 book arrived unbidden. A hefty tome with a cover featuring a younger version of her, smiling brightly. The title, "Eleanor Vance: A Life Unveiled," was printed in elegant script. A tremor ran through her hand as she lifted it. She hadn't authorized any biography.

Later, she sat in her sunroom, the afternoon light warming the pages. The prose was oddly familiar, like eavesdropping on her own thoughts. It detailed her childhood fears, her youthful ambitions, her secret crushes – all things only she knew, or so she thought. A coldness settled in her stomach.

She slammed the book shut. The narrative felt… manipulated. An almost sinister control over her past. Every detail, perfectly placed, seemed to hint at an agenda she couldn't yet identify. She needed answers. This felt like a violation.

Emotion: suspicious

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.82 Negative
PC2 (Disposition): 0.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤔0.420
🤔0.415
🧐0.362
疑0.352
suspicious0.352
Suppressed:
and-0.307
alleviate-0.301
ได้รับการ-0.298
allevi-0.285
mouthful-0.284