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 vibrant colors of the wedding decorations seemed to bleed together before her eyes. She caught sight of him, standing near the bar, talking casually to a few mutual acquaintances. A knot formed in her stomach, tightening with each passing second.

She forced herself to take a deep breath, trying to regain control. Her hands felt clammy, her heart hammered against her ribs. She was suddenly acutely aware of every detail of the room: the bright lights, the swirling patterns on the dance floor, the perfume of the other guests.

She busied herself with rearranging a napkin, her movements jerky and unnatural. She wanted to disappear, to dissolve into the background. The familiar faces of her friends offered no solace, no comfort. She felt alone, adrift.

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