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 world felt lighter, cleaner, thought Maya. She felt an almost childlike glee as she bounded towards the park. She had a skip in her step, a song on her lips. She felt free.

As she rounded the bend, the melody died in her throat. The place where the sapling had grown, the tree sheโ€™d nurtured for years, was bare. A knot formed in her throat, making it difficult to breathe. The lightness inside her was instantly replaced by a leaden weight.

"No," she gasped, her voice barely above a whisper. Her shoulders slumped, and the joy of the morning withered away.

Emotion: refreshed

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.998
de0.703
!).0.384
(!)0.381
!".0.379
Suppressed:
S-0.782
C-0.478
L-0.414
๐Ÿ˜ฃ-0.388
๐Ÿ˜ž-0.376