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 key had just been turned in the lock. Maya spun around, her arms wide. β€œI can’t believe it! Finally, a place to call my own!” she exclaimed aloud, her voice filled with a giddy energy. She practically skipped through the rooms, mentally planning where everything would go.

While examining the basement, she noticed a strange outline in the wall beneath the stairs. Intrigued, she started feeling around, her fingertips tracing the edges. A panel clicked open, revealing a small staircase leading down. A bubbling laugh escaped her. This was going to be the best.

Taking a deep breath, she started down the stairs, eager to see what secrets lay hidden.

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
😞-0.470
😣-0.337
L-0.334