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 surveyor's flag, a bright orange beacon, marked the property line. He stared at it, the plastic fluttering in the breeze. Mr. Chen had been polite, but insistent. The birch, beautiful as it was, needed to be removed.

He walked over to the tree, resting his hand against its cool trunk. He felt a sudden, sharp pang of distress. The thought of the empty space, the sun fully pouring in, was unbearable.

He didn't know how to navigate this, and yet he knew he must. He took a deep, shuddering breath, then walked back inside. The air felt thick, heavy with unspoken obligations.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288