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 sun streamed through the window, illuminating the dust motes dancing in the air, a scene that should have been calming, but instead, it amplified her unease. “Okay, so this is the final budget reconciliation,” she told the new trainee, a young man with overly-slicked hair, whose name she couldn’t even remember. She kept tripping over her words.

She felt a strange disconnect from her body, as if she were watching herself from outside. Her hands felt clammy, and she found herself repeatedly adjusting her glasses, a nervous tic she hadn't realized she had. The hum of the server room, usually background noise, now grated on her nerves. She felt a sudden, urgent need to escape, to run.

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