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).

He bounced his leg, a frantic rhythm against the hard plastic of the waiting room chair. The silence was suffocating, punctuated only by the rhythmic hum of the fluorescent lights. His hands were damp, and he kept wiping them on his jeans. The air in the room felt thick, almost unbreathable.

He ran a hand through his already disheveled hair, leaving it standing on end. He focused on the patterns in the linoleum floor, trying to distract himself. A bead of sweat trickled down his temple. He had to know. The future of everything was in this email.

The notification popped up, displaying the subject line: “Scholarship Decision.” He felt a pressure in his chest, making it hard to take a full breath. When he opened the email his world blurred and his jaw tightened.

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
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210