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).

Rain lashed against the windows of "The Golden Wok," mirroring the turmoil brewing inside Marcus. He reread the printed notice taped to the door: "Thank you for the memories." It seemed too… tidy.

He found himself scrutinizing the usually bustling kitchen, now eerily quiet. The scent of sesame oil, once a source of pure joy, now felt cloying, almost poisonous. Why were the normally boisterous cooks huddled together, whispering?

He approached the owner, Mr. Lee, who was meticulously polishing a chopstick. “Mr. Lee, I… I was surprised by the notice,” Marcus said, his voice hesitant. Mr. Lee’s smile didn’t reach his eyes, and his hand tightened around the chopstick.

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