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 phone vibrated insistently in Maya’s hand. Liam. Her heart did a strange flip-flop in her chest. They'd been sharing playlists and late-night talks for over a year, and now, he was on her friend's Instagram story – at the same concert, just a few feet away.

She felt a dizzying sensation, like the world was spinning. She should probably text him. It was the sensible thing to do. Her phone was clutched in a white-knuckled grip.

She decided to ignore it, to pretend this wasn't happening. Burying her face in her hands, Maya let out a shaky breath, whispering, "This can't be real."

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