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 cozy atmosphere of "The Cozy Corner Cafe" usually filled Michael with contentment. The sign, scrawled hastily on a chalkboard, read, "Closed." It felt…wrong.

He studied the empty tables and chairs, the silent coffee machine, the lifeless display of pastries. Everything seemed frozen in a state of unnatural stillness. He knew the owner, Mrs. Gable, personally, and the news was shocking.

Michael caught a glimpse of Mrs. Gable through the window. She was packing boxes, her face a mask of false indifference. He felt a chill run down his spine, a sense of foreboding that grew with each passing moment.

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