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 librarian, Mrs. Gable, almost dropped the letter, her hands trembling as she read the familiar script. It was from a student she'd scolded unjustly decades ago, and the apology was everything she'd never allowed herself to hope for. A flood of memories, both good and bad, washed over her. Her old, stern self seemed to fade into a memory.

She felt compelled to share this joy. She immediately began sorting through old photographs, searching for a picture of the student. Her steps became lighter as she moved, and she suddenly began to reorganize the library, determined to create a more welcoming space. She selected uplifting music for the background, a complete change from her normally quiet demeanor. Her world felt refreshed.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325