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 attic air hung thick with dust motes dancing in the single shaft of sunlight. Amelia clutched the yellowed paper, her knuckles white. It was her mother’s bucket list, scribbled in a looping, familiar hand. “Learn to tango.” Amelia tilted her head. Her mother hated dancing. It felt…off.

A knot tightened in her stomach. She reread the list, each item a small, everyday betrayal of the woman she thought she knew. “Visit the Grand Canyon.” Her mother had always professed a fear of heights. Why now?

She slowly lowered herself to the dusty floor. It was all a carefully constructed facade. A performance. Every memory, every story…a lie? The world tilted on its axis. She started to sweat.

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