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).

"Alright, children," Aunt Eleanor's lawyer droned, his voice like gravel. Amelia twirled a strand of hair, barely able to contain herself. Her brother, Charles, sat rigid beside her, face set in stone. Sheโ€™d always adored their eccentric aunt.

"For Amelia, my collection of vintage hats, and the sum of five thousand dollars." A small squeal escaped her lips. Five thousand dollars! And hats! Amelia practically vibrated with excitement, already picturing herself in a fabulous cloche.

Charles, the lawyer continued, was bequeathed โ€œmy vast collection of gardening tools, and the property at number 47 Willow Creek Lane.โ€ Amelia glanced at her brother. Gardening tools. He hated gardening! Her smile widened. This day was perfect.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
๐Ÿ˜ž-0.470
๐Ÿ˜ฃ-0.337
L-0.334