Fun post! Back during the holidays we wrote one where we abused temperature AND structured output to approximate a random selection: https://bits.logic.inc/p/all-i-want-for-christmas-is-a-rando...
When you asked it to choose by picking a random number between 1 and 4, it skewed the results heavily to 2 and 3. It could have interpreted your instructions to mean literally between 1 and 4 (not inclusive).