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 contents of the list were in neat, deliberate handwriting, the kind of handwriting she'd always loved. But as she read through the entries, a strange, suffocating feeling enveloped her. She found it in the pocket of his favorite jacket. The list was for a life apart.

She sat on the edge of the bed, the list trembling in her hands. Each item was a stark contrast to their shared reality. It was a list that felt more like a goodbye.

Later, she found herself staring at him from across the dinner table. Every smile, every touch, was a lie, she felt. The world around her blurred, and the only thing that felt real was the growing sense of dread.

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