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 courtroom felt suffocating. The air hung thick with the scent of stale paper and unspoken dread. Sarah clutched the crumpled tissue in her hand. She had just texted the lawyer in her divorce case, "How are we looking? Ready to fight?" Except, with shaking hands, she'd texted it to her soon-to-be ex-husband.

She felt a wave of dizziness. She pictured him, his face a mask of smug satisfaction. The implications of this message. He knew she was ready to fight. She imagined the smirk, the gloating.

She fought to keep her voice steady. The lawyer would be here any minute. She took a deep, shaky breath, attempting to calm the rapid-fire racing of her heart.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
ç·Šå¼µ0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210