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 world felt distorted, like looking through a funhouse mirror. Liam's graffiti, his raw, unapologetic expressions of urban life, were framed, commodified, hung in this fancy art space. He hadn't wanted this. He preferred the thrill of the chase, the illicit act, the temporary nature of it all. This… this was permanent, official, and it felt like a violation.

He paced the gallery, his boots thudding on the polished floor. Each of his pieces, once vibrant and defiant, now seemed muted, stripped of their original energy. He ran a hand over his jaw, feeling a tremor in his fingers. He imagined himself, crouched in the shadows, creating something new. The thought brought a small, fleeting comfort, but the feeling of unease remained, a persistent shadow.

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
πŸ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274