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 car ride had been excruciating. Sarah had felt like a tightly wound spring, ready to snap. Her brother, Mark, had been unusually quiet, his eyes fixed on the passing scenery. Now, they sat in a stuffy room, the solicitor’s gaze a sharp, assessing one. Sarah’s palms were slick.

The will reading began. Mark received a substantial sum and a collection of rare, first-edition books. Sarah, however, received… nothing. Panic seized her, a cold knot forming in her stomach. Then, the solicitor cleared his throat, the silence stretching.

"…and a key to a safe deposit box, containing…" He stopped to rearrange a stack of papers. “A vintage Rolls Royce and all the documents relating to its upkeep.” Sarah felt a strange lightness, a dizzying blend of disbelief and joy.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376