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 letter arrived in the mail, crisp and official. "The Spice Route" was closing its doors. James ran a hand through his hair, a nervous gesture he hadn't realized he was making. This felt wrong. He'd been going there since he was a kid.

He found himself pacing his living room, the familiar space feeling suddenly constricting. He stopped in front of the window, staring out at the street, a place that felt unfamiliar. His chest felt constricted. His hands felt cold.

He wanted to argue, to deny it, to find some loophole. He felt a deep ache, a void where familiarity once existed. This was more than just the end of a restaurant; it was the end of a chapter.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274