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 old house creaked and groaned in the autumn wind. Mark, home for a visit, found himself in the attic, surrounded by the ghosts of his childhood. In a dusty box, he discovered a collection of his niece, Chloe's, drawings. He saw the drawings, all of a tall man with mismatched shoes.

His breath hitched. That was “Silas.” His imaginary friend. He had forgotten all about him.

He felt a familiar ache in his heart, a deep longing for the companionship he had once found in the imaginary world. He knew what it was like to feel lost and alone.

He made a mental note to spend extra time with Chloe, to listen to her stories, and to encourage her imagination. He knew she needed this friend.

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296