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 room seemed to shrink around Liam as he unfolded the letter. He’d found it in a box of his grandmother's things, written in her elegant script and addressed to his grandfather, who had passed away years ago.

He could feel a tremor starting in his hands and spreading through him. The letter spoke of a life unlived, of dreams deferred, and of the unspoken words that had remained trapped between them.

He suddenly felt claustrophobic, the walls of the room closing in. He let out a strangled groan, his breath coming in ragged gasps. He needed to get out, to escape the suffocating weight of the past.

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
λ‹€μ‹œ0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290