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 office felt unusually warm, the air conditioning doing little to combat the building heat. Sarah kept fidgeting with the pen on her desk, clicking it incessantly. It was a habit she knew annoyed people, including herself.

She stole a glance at Mark's desk across the way. He was lost in his work, a stark contrast to her internal chaos. He was always so calm, so collected. They were both up for the senior project manager role, a coveted position within the company.

Each email notification, each phone call made her jump, a sudden spike of adrenaline surging through her. She felt like a tight wire, stretched to the breaking point. She needed this, she wanted this, but the thought of potentially losing out to Mark, of witnessing his success, felt like a physical blow.

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