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).

"Well, this is going to change things, isn't it?" Chloe mumbled to herself, her eyes glued to the letter. Her mother had kept this secret for thirty years! A brother. A *brother* she never knew existed. She began pacing, a tight energy coursing through her.

She ran her hand over her hair, a nervous gesture. She picked up her phone and dialed her mother’s number immediately. The phone rang and rang, but Chloe kept staring at the phone, willing her mother to answer. She needed details. Now.

Her mind raced with possibilities. Where did he live? What did he like? Would he even *want* to meet her? She bit her lip and then, after the call went to voicemail, she shot a quick text: "Mom, call me ASAP. Urgent."

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