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 lawyer’s office smelled of old paper and dust. Amelia slammed the worn leather portfolio onto the mahogany desk. “Are you *sure* this is correct?” Her voice was tight, a thin wire stretched taut. Her brother, Thomas, leaned back in his chair, a smug look plastered across his face.

She glared at the document. Her inheritance: a crumbling cottage on the edge of the marshes, a property she knew was infested with damp. Thomas, however, had inherited the family business: a thriving chain of luxury hotels. Her jaw clenched. She hated the way he’d been so… eager to get here.

Amelia’s fingers tightened on the portfolio. The lawyer, a small, birdlike man with watery eyes, cleared his throat. “Yes, Miss. Your father’s will is quite clear.” He averted his gaze. She felt a heat rising in her chest.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256