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 rain hammered against the windows as Daniel sat by the fire, reading. The letter, discovered in a tattered copy of *Moby Dick*, spoke of a betrayal, a loss. He found himself unable to breathe comfortably, as if a weight rested on his chest. His usual calm was frayed, unraveling.

He rose from the chair, a feeling of restlessness overtaking him. He stared out the window, at the storm-tossed trees, each branch silhouetted against the tumultuous sky. The wind howled, a sound that seemed to mimic the turmoil inside him. He felt an intense need to *do* something, to break free of this stifling… feeling. He slammed his fist against the windowsill, a sharp, angry sound that echoed in the otherwise quiet room.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284