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).

Mr. Chen, weary of endless meetings and administrative paperwork, slumped at his desk. He was ready to quit. A student, Maria, now a successful musician, had always been a source of both frustration and pride. He saw her talent, but she was a handful. An unmarked package arrived.

Inside, was a beautifully crafted, custom-made ukulele. A note, short and sweet, read, "For the teacher who heard my music." He picked up the instrument and carefully plucked a string.

A smile spread across his face, he closed his eyes and started strumming. The sound, simple and clear, filled the room. The mundane worries faded away, and he began humming a familiar tune, a feeling of genuine joy bubbling within him.

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.613
!0.544
B0.508
🤩0.499
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341