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 was abruptly out of focus. Sarah blinked, attempting to refocus her gaze on the stark words of the notice. Her heart thumped a frantic rhythm against her ribs. The small apartment, usually a refuge, now felt like a cage.

She began pacing, the wooden floors creaking under her hurried steps. Every shadow seemed to lengthen, the familiar sounds of the city outside – the distant sirens, the chatter of neighbors – now amplified into a symphony of dread. She felt a sharp pain in her chest, a physical manifestation of her fear.

She clutched her head, fingers digging into her scalp. Her throat felt tight, and she struggled to swallow. Every breath felt shallow and insufficient.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290