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 waiting room seemed to shrink, the silence pressing in around her, suffocating. The air was thick with unspoken anxieties, the scent of disinfectant a constant reminder of the situation. The diagnosis - a shared journey. She felt a knot tighten in her stomach.

She saw him then, a man across the room, his face etched with a similar blend of confusion and alarm. He caught her eye, and the unspoken acknowledgment hung between them like a fragile thread.

She rose, her movements stiff. Each step felt deliberate, a conscious effort to navigate the treacherous landscape of her own emotions. She felt a strange pull toward him, an undeniable connection in the face of the unknown.

She found herself walking towards him. He looked up at her approach, and their gazes locked for a long moment, before he broke eye contact.

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