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 silence in the apartment was deafening, the quiet after the phone call even worse. Every morning, she would wake up, feeling a knot of anxiety in her stomach. Every night, it would tighten further. He’d been taking calls in the car, on his lunch break, even when they went for a walk. Always a different number, always a different tone.

She couldn’t eat. The food tasted like ash in her mouth. She couldn't sleep. The darkness of the bedroom felt like a void, threatening to swallow her whole.

She had to know. The feeling in her gut, a low, persistent thrum of unease, was becoming unbearable. The uncertainty was a corrosive poison, eating away at her from the inside out.

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