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 weight of the world lifted as Daniel stepped out of the library, the completed draft of his thesis burning a hole in his backpack. He breathed deeply, feeling the crisp autumn air fill his lungs. He felt giddy with accomplishment, ready to celebrate. The feeling was short lived, however. A curt email arrived from his advisor, subject: Academic Integrity Investigation. He stood frozen, the wind suddenly chilling.

He stood before the committee, attempting to appear composed, but his hands betrayed him, fidgeting nervously. The room felt stifling.

As he listened to the accusations, his heart began to pound against his ribs. He attempted to explain his process, his voice barely a whisper at first, slowly gaining strength as he defended his work.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422