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).

"You're shifting to libero, Sasha," her coach had declared, the words hanging in the tense silence of the volleyball court. Sasha, a star outside hitter, felt the blood drain from her face.

Her hands, usually strong and steady, trembled as she touched the volleyball. The shift to a defensive role felt like a betrayal of her training.

She watched the other players move through their warm-ups, their movements effortless. A fresh pang of doubt filled her.

She took a deep breath, trying to regain her composure. This wasn't her role. Her stomach clenched again. The court felt different, the net a barrier.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234