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 city pulsed around Maya. The concrete vibrated beneath her feet. She skipped along the sidewalk, dodging pedestrians with a laugh. She had just finished a painting, a wild explosion of color that had consumed her for weeks. The feeling was intoxicating. She needed more.

She ducked into a small, cluttered antique shop. She felt drawn to a worn copy of "Wuthering Heights." As she opened the book, something slid out and landed on the floor: a photograph. The sepia tones depicted a laughing woman, her eyes crinkling at the corners.

Maya felt a connection, a shared surge of something similar to the feeling she had. She studied the photograph, captivated. She immediately grabbed her sketchbook, wanting to capture the energy of this unknown woman.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306