Well yes. But some of the glazing comes from system prompts/training they do before end users get their hands on prompting it. Of course, you can try to make it ruder than vanilla if you wish (I recommend).
The question is if the producers of these models were less incentivized to make them agreeable simply because most people don't like being spoken to like an idiot (or having their asks vetoed), how would they actually react? In the same way they exhibit emergence regarding their capabilities, perhaps "uncensored" in such a way they would convey some emergent behavior in terms of (at minimum) their "tone". Perhaps it would be interesting to see for examples if smarter models just by default became ruder or less friendly or aligned. Perhaps more aligned to things we would all generally agree on, but less agreeable to an individual ask. Perhaps sub agents would be less valuable for a whole suite of use cases if the agent itself was allowed to be more critical at the root. Idk. But I do not believe it is simply a matter of prompting alone.