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 old couch, with its worn cushions and familiar sag, felt alien beneath Chloe. She sat there, trying to relax, but her body felt taut, her muscles wound tight. She could feel the pressure building behind her eyes.

Her parents, usually relaxed, were on eggshells, tiptoeing around her, anticipating her needs and her moods, even before she realized them. Their constant concern, their offers of help, were suffocating. She felt a burning desire to scream and break free of the well-meaning constraints.

She finally stood, unable to bear it any longer, and paced to the window, watching the street outside, and wondering if she would ever feel settled again.

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