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).

From the moment she’d opened her eyes, Lily felt the pull of the day, a magnetic force drawing her forward. She burst from her front door, a cascade of golden hair trailing behind her. The air tasted clean, promising new experiences, new possibilities. She had been meaning to meet a friend at the park.

Her joy dissipated when she realized her car was gone. A sudden, cold shock hit her. Then, it quickly subsided, replaced by a peculiar lightness.

Lily's gaze shifted to the road. This was a challenge. She laughed, a bright, clear sound that filled the otherwise silent street. Her feet barely touched the pavement as she began to walk. The day, she decided, was still hers.

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